Dynamic Entity Representation with Max-pooling Improves Machine Reading

Sosuke Kobayashi, Ran Tian, Naoaki Okazaki, Kentaro Inui

Abstract: We propose a novel neural network model for machine reading, DER Network, which explicitly implements a reader building dynamic meaning representations for entities by gathering and accumulating information around the entities as it reads a document. Evaluated on a recent large scale dataset (Hermann et al., 2015), our model exhibits better results than previous research, and we find that max-pooling is suited for modeling the accumulation of information on entities. Further analysis suggests that our model can put together multiple pieces of information encoded in different sentences to answer complicated questions. Our code for the model is available at https://github. com/soskek/der-network